News for hackers. Stuff that matters.
Re:AllenNLP – An open-source NLP research library, built on ... by glup on Saturday September 16, 2017 @12:16PM (#15265267)
All of the above require fairly complex world knowledge as well as an explicit representation of a scene. There is minimal leverage for lexical distributional statistics in these cases—arguably the one thing we have had major success in using (e.g. building vector space word representations, like Word2Vec; finding the highest probability parse tree for an utterance).

There are no comments on this comment yet.